Pinned Repositories
fastT5
⚡ boost inference speed of T5 models by 5x & reduce the model size by 3x.
ICL-benchmark
A simple benchmark for In-Context Learning inspired by Hyena (https://arxiv.org/abs/2302.10866)
kinda-llama
An open-source replication and extension of the Meta AI's LLAMA dataset
magma
MAGMA - a GPT-style multimodal model that can understand any combination of images and language. NOTE: The freely available model from this repo is only a demo. For the latest multimodal and multilingual models from Aleph Alpha check out our website https://app.aleph-alpha.com
Open-Assistant
RWKV-LM
RWKV is a RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference, saves VRAM, fast training, "infinite" ctx_len, and free sentence embedding.
ul2
ul2 but smol
yuxdux's Repositories
yuxdux/kinda-llama
An open-source replication and extension of the Meta AI's LLAMA dataset
yuxdux/ICL-benchmark
A simple benchmark for In-Context Learning inspired by Hyena (https://arxiv.org/abs/2302.10866)
yuxdux/fastT5
⚡ boost inference speed of T5 models by 5x & reduce the model size by 3x.
yuxdux/magma
MAGMA - a GPT-style multimodal model that can understand any combination of images and language. NOTE: The freely available model from this repo is only a demo. For the latest multimodal and multilingual models from Aleph Alpha check out our website https://app.aleph-alpha.com
yuxdux/Open-Assistant
yuxdux/RWKV-LM
RWKV is a RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference, saves VRAM, fast training, "infinite" ctx_len, and free sentence embedding.
yuxdux/ul2
ul2 but smol